Olisaemeka F. Isife, Kennedy Okokpujie, Imhade P. Okokpujie, Roselyn E. Subair, Akingunsoye Adenugba Vincent, Morayo E. Awomoyi
With the exponential surge in the number of internet-connected devices, the attack surface for potential cyber threats has correspondingly expanded. Such a landscape necessitates the evolution of intrusion detection systems to counter the increasingly sophisticated mechanisms employed by cyber attackers. Traditional machine learning methods, coupled with existing deep learning implementations, are observed to exhibit limited proficiency due to their reliance on outdated datasets. Their performance is further compromised by elevated false positive rates, decreased detection rates, and an inability to efficiently detect novel attacks. In an attempt to address these challenges, this study proposes a deep learning-based system specifically designed for the detection of malicious network traffic. Three distinct deep learning models were employed: Deep Neural Networks (DNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU). These models were trained using two contemporary benchmark intrusion detection datasets: the CICIDS 2017 and the Coburg Intrusion Detection Data Sets (CIDDS). A robust preprocessing procedure was conducted to merge these datasets based on common and essential features, creating a comprehensive dataset for model training. Two separate experimental setups were utilized to configure these models. Among the three models, the LSTM displayed superior performance in both experimental configurations. It achieved an accuracy of 98.09%, a precision of 98.14%, an F1-Score of 98.09%, a True Positive Rate (TPR) of 98.05%, a True Negative Rate (TNR) of 99.69%, a False Positive Rate (FPR) of 0.31%, and a False Negative Rate (FNR) of 1.95%.
{"title":"Development of a Malicious Network Traffic Intrusion Detection System Using Deep Learning","authors":"Olisaemeka F. Isife, Kennedy Okokpujie, Imhade P. Okokpujie, Roselyn E. Subair, Akingunsoye Adenugba Vincent, Morayo E. Awomoyi","doi":"10.18280/ijsse.130401","DOIUrl":"https://doi.org/10.18280/ijsse.130401","url":null,"abstract":"With the exponential surge in the number of internet-connected devices, the attack surface for potential cyber threats has correspondingly expanded. Such a landscape necessitates the evolution of intrusion detection systems to counter the increasingly sophisticated mechanisms employed by cyber attackers. Traditional machine learning methods, coupled with existing deep learning implementations, are observed to exhibit limited proficiency due to their reliance on outdated datasets. Their performance is further compromised by elevated false positive rates, decreased detection rates, and an inability to efficiently detect novel attacks. In an attempt to address these challenges, this study proposes a deep learning-based system specifically designed for the detection of malicious network traffic. Three distinct deep learning models were employed: Deep Neural Networks (DNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU). These models were trained using two contemporary benchmark intrusion detection datasets: the CICIDS 2017 and the Coburg Intrusion Detection Data Sets (CIDDS). A robust preprocessing procedure was conducted to merge these datasets based on common and essential features, creating a comprehensive dataset for model training. Two separate experimental setups were utilized to configure these models. Among the three models, the LSTM displayed superior performance in both experimental configurations. It achieved an accuracy of 98.09%, a precision of 98.14%, an F1-Score of 98.09%, a True Positive Rate (TPR) of 98.05%, a True Negative Rate (TNR) of 99.69%, a False Positive Rate (FPR) of 0.31%, and a False Negative Rate (FNR) of 1.95%.","PeriodicalId":37802,"journal":{"name":"International Journal of Safety and Security Engineering","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135420780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Deebakkarthi Chinnasame Rani, Sai Ganesh Janakiraman, Kommula Serath Chandra, Elambharathi Padmavathi Thangavel, Ganga Abhirup Kothamasu, Krithika Latha Bhaskaran, Guruprakash Jayabalasamy
Presented herein is a novel algorithm for multi-round, zero-knowledge proof (ZKP), devised specifically for authenticating factorisation proofs within a variety of cryptographic applications. This advanced algorithm, while maintaining computational complexity within acceptable bounds, offers a secure and proficient solution. The functionality of the algorithm is marked by multiple rounds of interaction between the Prover and Verifier. Initially, the Prover generates a random value and calculates a commitment. Subsequently, the Verifier issues a random challenge, eliciting a computed response from the Prover. To validate the proof, the Verifier verifies the equality of the commitment and the computed response. Efficaciousness of the proposed multi-round ZKP algorithm is demonstrated across diverse input sizes and parameters. Results indicate a success rate exceeding 90% on average, showcasing the robustness of the method. The recurring interaction between the Verifier and Prover enhances the Prover's authentication, thereby improving the algorithm’s reliability. Implementation of the algorithm, achievable through standard cryptographic tools and protocols, can fortify the security of multiple cryptographic applications. A significant application can be found in Digital Identity Management Systems (DIMS). Currently, these systems are vulnerable to a myriad of threats, including identity spoofing, data breaches, and internal security risks. The application of the ZKP algorithm can simultaneously augment security and withhold sensitive information, potentially transforming the DIMS security landscape. Future research may focus on improving the efficiency and scalability of the multi-round ZKP algorithm. There also remains a vast potential for exploring additional applications of this technique within various cryptographic domains.
{"title":"A Multi-Round Zero Knowledge Proof Algorithm for Secure IoT and Blockchain Environments","authors":"Deebakkarthi Chinnasame Rani, Sai Ganesh Janakiraman, Kommula Serath Chandra, Elambharathi Padmavathi Thangavel, Ganga Abhirup Kothamasu, Krithika Latha Bhaskaran, Guruprakash Jayabalasamy","doi":"10.18280/ijsse.130408","DOIUrl":"https://doi.org/10.18280/ijsse.130408","url":null,"abstract":"Presented herein is a novel algorithm for multi-round, zero-knowledge proof (ZKP), devised specifically for authenticating factorisation proofs within a variety of cryptographic applications. This advanced algorithm, while maintaining computational complexity within acceptable bounds, offers a secure and proficient solution. The functionality of the algorithm is marked by multiple rounds of interaction between the Prover and Verifier. Initially, the Prover generates a random value and calculates a commitment. Subsequently, the Verifier issues a random challenge, eliciting a computed response from the Prover. To validate the proof, the Verifier verifies the equality of the commitment and the computed response. Efficaciousness of the proposed multi-round ZKP algorithm is demonstrated across diverse input sizes and parameters. Results indicate a success rate exceeding 90% on average, showcasing the robustness of the method. The recurring interaction between the Verifier and Prover enhances the Prover's authentication, thereby improving the algorithm’s reliability. Implementation of the algorithm, achievable through standard cryptographic tools and protocols, can fortify the security of multiple cryptographic applications. A significant application can be found in Digital Identity Management Systems (DIMS). Currently, these systems are vulnerable to a myriad of threats, including identity spoofing, data breaches, and internal security risks. The application of the ZKP algorithm can simultaneously augment security and withhold sensitive information, potentially transforming the DIMS security landscape. Future research may focus on improving the efficiency and scalability of the multi-round ZKP algorithm. There also remains a vast potential for exploring additional applications of this technique within various cryptographic domains.","PeriodicalId":37802,"journal":{"name":"International Journal of Safety and Security Engineering","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135386314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Desiderius V. Indrayana, Krishna S. Pribadi, Puti F. Marzuki, Hardianto Iridiastadi
The construction sector in Indonesia witnesses a significant number of work accidents, with construction sites being particularly prone to such incidents. It is imperative for stakeholders, especially project owners, to prioritize safety performance. The authorization of safety plans empowers project owners, granting them substantial influence over safety outcomes. This research employs Structural Equation Modeling (SEM) to investigate the relationship between project owners' safety leadership and safety performance, with valuable input obtained from contractors who directly interact with project owners. The identified variables encompass leader's maturity attributes, psychosocial factors, participatory approaches, communication practices, and competence levels. All interrelationships between the variables demonstrate high significance in shaping safety performance (with z-scores exceeding 1.96). Two distinct patterns are identified to characterize project owners' leadership styles. The first pattern relates to the personal maturity of the owner, while the second pattern focuses on the owner's ability to foster effective stakeholder relationships. To manifest maturity, project owners must make three key contributions: 1) ensuring safety costs are factored into the project value, 2) procuring contractors with well-defined safety policies, and 3) ensuring swift responses to accidents. These findings underscore the importance of project owners in enhancing construction safety practices, emphasizing their role beyond that of contractors.
{"title":"Safety Leadership and Performance in Indonesia’s Construction Sector: The Role of Project Owners’ Marurity","authors":"Desiderius V. Indrayana, Krishna S. Pribadi, Puti F. Marzuki, Hardianto Iridiastadi","doi":"10.18280/ijsse.130405","DOIUrl":"https://doi.org/10.18280/ijsse.130405","url":null,"abstract":"The construction sector in Indonesia witnesses a significant number of work accidents, with construction sites being particularly prone to such incidents. It is imperative for stakeholders, especially project owners, to prioritize safety performance. The authorization of safety plans empowers project owners, granting them substantial influence over safety outcomes. This research employs Structural Equation Modeling (SEM) to investigate the relationship between project owners' safety leadership and safety performance, with valuable input obtained from contractors who directly interact with project owners. The identified variables encompass leader's maturity attributes, psychosocial factors, participatory approaches, communication practices, and competence levels. All interrelationships between the variables demonstrate high significance in shaping safety performance (with z-scores exceeding 1.96). Two distinct patterns are identified to characterize project owners' leadership styles. The first pattern relates to the personal maturity of the owner, while the second pattern focuses on the owner's ability to foster effective stakeholder relationships. To manifest maturity, project owners must make three key contributions: 1) ensuring safety costs are factored into the project value, 2) procuring contractors with well-defined safety policies, and 3) ensuring swift responses to accidents. These findings underscore the importance of project owners in enhancing construction safety practices, emphasizing their role beyond that of contractors.","PeriodicalId":37802,"journal":{"name":"International Journal of Safety and Security Engineering","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135386386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pedro P. Rojas, Cindy Moya, Martha Caballero, Wilmer Márquez, Josué Briones-Bitar, Fernando Morante-Carballo
This research, conducted in Zaruma, southern Ecuador, seeks to evaluate the seismic vulnerability and performance level of the Humberto Molina Hospital's reinforced concrete buildings. The study employs an examination of national and international seismic codes for rehabilitation, along with the implementation of recommended techniques. Structural characteristics of the buildings were identified through auscultation, surveys of reinforcing steel, and the extraction of concrete cores. The amassed data, coupled with a seismic hazard analysis of the site, facilitated a structural assessment of the blocks, conducted in accordance with national (MIDUVI) and international (ASCE/SEI) codes. The Federal Emergency Management Agency (FEMA) subsequently proposed rehabilitation alternatives for each block. Due to the importance of the hospital's functions, data collection was limited to blocks B3 and B4. The structural system, composed of moment-resisting concrete frames, exhibits potential vulnerabilities due to knocking (collision) and torsion, attributed to its irregular form. Structural evaluation revealed that block B4 adheres to the drift limits stipulated by the ASCE 41-13 standard (below 2%), while block B3 exceeds these limits (2.05-2.80%). Recommended rehabilitation strategies for B3 encompass mass reduction (removal of the second floor, representing a dead load of 700kg/m 2 and a live load of 200kg/m 2 ), and the introduction of additional rigidity and strength (extension of structural elements). For block B4, it is suggested that each sub-block be made independent. These interventions aim to facilitate the hospital's reopening, thereby benefiting the Zaruma Mining District community.
{"title":"Assessing and Mitigating Seismic Risk for a Hospital Structure in Zaruma, Ecuador: A Structural and Regulatory Evaluation","authors":"Pedro P. Rojas, Cindy Moya, Martha Caballero, Wilmer Márquez, Josué Briones-Bitar, Fernando Morante-Carballo","doi":"10.18280/ijsse.130402","DOIUrl":"https://doi.org/10.18280/ijsse.130402","url":null,"abstract":"This research, conducted in Zaruma, southern Ecuador, seeks to evaluate the seismic vulnerability and performance level of the Humberto Molina Hospital's reinforced concrete buildings. The study employs an examination of national and international seismic codes for rehabilitation, along with the implementation of recommended techniques. Structural characteristics of the buildings were identified through auscultation, surveys of reinforcing steel, and the extraction of concrete cores. The amassed data, coupled with a seismic hazard analysis of the site, facilitated a structural assessment of the blocks, conducted in accordance with national (MIDUVI) and international (ASCE/SEI) codes. The Federal Emergency Management Agency (FEMA) subsequently proposed rehabilitation alternatives for each block. Due to the importance of the hospital's functions, data collection was limited to blocks B3 and B4. The structural system, composed of moment-resisting concrete frames, exhibits potential vulnerabilities due to knocking (collision) and torsion, attributed to its irregular form. Structural evaluation revealed that block B4 adheres to the drift limits stipulated by the ASCE 41-13 standard (below 2%), while block B3 exceeds these limits (2.05-2.80%). Recommended rehabilitation strategies for B3 encompass mass reduction (removal of the second floor, representing a dead load of 700kg/m 2 and a live load of 200kg/m 2 ), and the introduction of additional rigidity and strength (extension of structural elements). For block B4, it is suggested that each sub-block be made independent. These interventions aim to facilitate the hospital's reopening, thereby benefiting the Zaruma Mining District community.","PeriodicalId":37802,"journal":{"name":"International Journal of Safety and Security Engineering","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135386538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the endeavor to halt the transmission of infectious diseases, containment and isolation emerge as pivotal preventive strategies. The elucidation of disease spread dynamics, through the lens of mathematical models, is instrumental in forecasting epidemiological trajectories. This study presents an augmented Susceptible-Infected-Recovered (SIR) model, assimilating these preventive measures, to scrutinize the propagation of COVID-19 since its initial emergence. The combat against this pandemic has predominantly hinged upon non-pharmaceutical interventions (NPIs) including, but not limited to, mask utilization, physical distancing, patient isolation, contact quarantine, and hand hygiene. The focal point of our investigation lies in the examination of the influence of susceptible population containment and infected individual isolation on the evolution of the ongoing outbreak. The basic reproductive number, an indicator of contagiousness, is analyzed over the course of the outbreak, yielding promising outcomes.
{"title":"Improving the SIR Model: Isolation and Containment Strategies for COVID-19 - A Case Study of Ain-Touta City","authors":"Assia Aouachria, Moussa Anoune, Soraya Yebbal, Zeroual Aouachria","doi":"10.18280/ijsse.130418","DOIUrl":"https://doi.org/10.18280/ijsse.130418","url":null,"abstract":"In the endeavor to halt the transmission of infectious diseases, containment and isolation emerge as pivotal preventive strategies. The elucidation of disease spread dynamics, through the lens of mathematical models, is instrumental in forecasting epidemiological trajectories. This study presents an augmented Susceptible-Infected-Recovered (SIR) model, assimilating these preventive measures, to scrutinize the propagation of COVID-19 since its initial emergence. The combat against this pandemic has predominantly hinged upon non-pharmaceutical interventions (NPIs) including, but not limited to, mask utilization, physical distancing, patient isolation, contact quarantine, and hand hygiene. The focal point of our investigation lies in the examination of the influence of susceptible population containment and infected individual isolation on the evolution of the ongoing outbreak. The basic reproductive number, an indicator of contagiousness, is analyzed over the course of the outbreak, yielding promising outcomes.","PeriodicalId":37802,"journal":{"name":"International Journal of Safety and Security Engineering","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135386547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Leveraging Security Modeling and Information Systems Audits to Mitigate Network Vulnerabilities","authors":"Laberiano Andrade Arenas, Cesar Yactayo-Arias, Sheyla Rivera Quispe, Jenner Lavalle Sandoval","doi":"10.18280/ijsse.130420","DOIUrl":"https://doi.org/10.18280/ijsse.130420","url":null,"abstract":"ABSTRACT","PeriodicalId":37802,"journal":{"name":"International Journal of Safety and Security Engineering","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135386771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"SE-CDR: Enhancing Security and Efficiency of Key Management in Internet of Energy Consumer Demand-Response Communications","authors":"Mourad Benmalek, Kamel Harkat, Kamel-Dine Haouam, Zakaria Gheid","doi":"10.18280/ijsse.130403","DOIUrl":"https://doi.org/10.18280/ijsse.130403","url":null,"abstract":"ABSTRACT","PeriodicalId":37802,"journal":{"name":"International Journal of Safety and Security Engineering","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135386887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The escalating frequency and complexity of cyber-attacks have necessitated the development of effective cyber forensic investigation techniques. This research investigates the utilization of machine learning and artificial intelligence (AI) in automated analysis and classification of cyber threats, aiming to enhance the understanding of their role in cyber forensics. Employing case studies, observations, and surveys, information was gathered from forensic investigators and cybersecurity experts. The case studies comprehensively examine organizations that have implemented AI and machine learning in cyber forensics. Observational methods involve attending conferences and closely observing investigators during forensic analysis. Survey data from forensic investigators and cybersecurity experts were collected to gain insights into the application of these novel investigation methods in cyber forensics. The findings demonstrate that AI and machine learning are emerging as powerful tools for augmenting cyber forensic investigations, particularly in the realms of threat detection and classification. The case studies reveal that businesses adopting these technologies have experienced notable improvements in the efficiency and precision of forensic investigations. This study underscores the potential advantages of integrating artificial intelligence and machine learning in advancing digital forensic investigations and provides valuable insights into their roles in cyber forensics. Accelerated analytical procedures and enhanced threat detection capabilities are evident outcomes of incorporating these technologies. By leveraging AI and machine learning, investigations can be expedited, enabling prompt responses to cyber threats and reducing overall risk exposure for businesses. As the cybersecurity landscape continues to evolve, the successful integration of AI and machine learning in the industry holds the promise of ushering in a new era of proactive threat detection, bolstering organizations' capacity to safeguard digital assets.
{"title":"Enhancing Cyber Forensics with AI and Machine Learning: A Study on Automated Threat Analysis and Classification","authors":"Bandr Fakiha","doi":"10.18280/ijsse.130412","DOIUrl":"https://doi.org/10.18280/ijsse.130412","url":null,"abstract":"The escalating frequency and complexity of cyber-attacks have necessitated the development of effective cyber forensic investigation techniques. This research investigates the utilization of machine learning and artificial intelligence (AI) in automated analysis and classification of cyber threats, aiming to enhance the understanding of their role in cyber forensics. Employing case studies, observations, and surveys, information was gathered from forensic investigators and cybersecurity experts. The case studies comprehensively examine organizations that have implemented AI and machine learning in cyber forensics. Observational methods involve attending conferences and closely observing investigators during forensic analysis. Survey data from forensic investigators and cybersecurity experts were collected to gain insights into the application of these novel investigation methods in cyber forensics. The findings demonstrate that AI and machine learning are emerging as powerful tools for augmenting cyber forensic investigations, particularly in the realms of threat detection and classification. The case studies reveal that businesses adopting these technologies have experienced notable improvements in the efficiency and precision of forensic investigations. This study underscores the potential advantages of integrating artificial intelligence and machine learning in advancing digital forensic investigations and provides valuable insights into their roles in cyber forensics. Accelerated analytical procedures and enhanced threat detection capabilities are evident outcomes of incorporating these technologies. By leveraging AI and machine learning, investigations can be expedited, enabling prompt responses to cyber threats and reducing overall risk exposure for businesses. As the cybersecurity landscape continues to evolve, the successful integration of AI and machine learning in the industry holds the promise of ushering in a new era of proactive threat detection, bolstering organizations' capacity to safeguard digital assets.","PeriodicalId":37802,"journal":{"name":"International Journal of Safety and Security Engineering","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135386591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Ultra-Lightweight Encryption for STL Files in IoT-based 3D Printing","authors":"Nilufar Yasmin, Richa Gupta","doi":"10.18280/ijsse.130407","DOIUrl":"https://doi.org/10.18280/ijsse.130407","url":null,"abstract":"","PeriodicalId":37802,"journal":{"name":"International Journal of Safety and Security Engineering","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135387185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Detecting Cyberbullying on Social Media Using Support Vector Machine: A Case Study on Twitter","authors":"None Al-Khowarizmi, Indah Purnama Sari, Halim Maulana","doi":"10.18280/ijsse.130413","DOIUrl":"https://doi.org/10.18280/ijsse.130413","url":null,"abstract":"ABSTRACT","PeriodicalId":37802,"journal":{"name":"International Journal of Safety and Security Engineering","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135386589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：